{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T20:38:16Z","timestamp":1776803896706,"version":"3.51.2"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247027","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"18692-18699","source":"Crossref","is-referenced-by-count":0,"title":["PrefMMT: Modeling Human Preferences in Preference-based Reinforcement Learning with Multimodal Transformers"],"prefix":"10.1109","author":[{"given":"Dezhong","family":"Zhao","sequence":"first","affiliation":[{"name":"Beijing University of Chemical Technology,College of Mechanical and Electrical Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Purdue University,SMART Laboratory,Department of Computer and Information Technology,West Lafayette,IN,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dayoon","family":"Suh","sequence":"additional","affiliation":[{"name":"Purdue University,SMART Laboratory,Department of Computer and Information Technology,West Lafayette,IN,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taehyeon","family":"Kim","sequence":"additional","affiliation":[{"name":"Purdue University,SMART Laboratory,Department of Computer and Information Technology,West Lafayette,IN,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziqin","family":"Yuan","sequence":"additional","affiliation":[{"name":"Purdue University,SMART Laboratory,Department of Computer and Information Technology,West Lafayette,IN,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byung-Cheol","family":"Min","sequence":"additional","affiliation":[{"name":"Purdue University,SMART Laboratory,Department of Computer and Information Technology,West Lafayette,IN,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guohua","family":"Chen","sequence":"additional","affiliation":[{"name":"Beijing University of Chemical Technology,College of Mechanical and Electrical Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981616"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989108"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341410"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3366414"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-019-01417-4"},{"key":"ref7","article-title":"B-pref: Benchmarking preference-based reinforcement learning","author":"Lee","year":"2021","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref8","article-title":"Surf: Semi-supervised reward learning with data augmentation for feedback-efficient preference-based reinforcement learning","author":"Park","year":"2022"},{"issue":"136","key":"ref9","first-page":"1","article-title":"A survey of preference-based reinforcement learning methods","volume":"18","author":"Wirth","year":"2017","journal-title":"Journal of Machine Learning Research"},{"key":"ref10","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref11","first-page":"6152","article-title":"Pebble: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training","volume-title":"International Conference on Machine Learning","author":"Lee"},{"key":"ref12","article-title":"Surf: Semi-supervised reward learning with data augmentation for feedback-efficient preference-based reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Park"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341912"},{"key":"ref14","article-title":"Sample-efficient preference-based reinforcement learning with dynamics aware rewards","volume-title":"7th Annual Conference on Robot Learning","author":"Metcalf"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981076"},{"key":"ref16","first-page":"22 270","article-title":"Meta-reward-net: Implicitly differentiable reward learning for preference-based reinforcement learning","volume":"35","author":"Liu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3528663"},{"key":"ref18","first-page":"1160","article-title":"Rewarding behaviors","volume-title":"Proceedings of the National Conference on Artificial Intelligence","author":"Bacchus"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/766"},{"key":"ref20","first-page":"27 652","article-title":"Non-markovian reward modelling from trajectory labels via interpretable multiple instance learning","volume":"35","author":"Early","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","article-title":"Preference transformer: Modeling human preferences using transformers for rl","volume-title":"The Eleventh International Conference on Learning Representations (ICLR)","author":"Kim"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3419106"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref24","first-page":"2226","article-title":"A trajectory is worth three sentences: multimodal transformer for offline reinforcement learning","author":"Wang","year":"2023","journal-title":"Uncertainty in Artificial Intelligence"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids53995.2022.10000239"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3074873"},{"key":"ref27","first-page":"4447","article-title":"A general theoretical paradigm to understand learning from human preferences","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Azar"},{"key":"ref28","article-title":"D4rl: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020"},{"key":"ref29","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Conference on robot learning","author":"Yu"},{"key":"ref30","article-title":"Reinforcement learning from diverse human preferences","author":"Xue","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128756"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"ref33","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","author":"Rafailov","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref34","article-title":"Inverse preference learning: Preference-based rl without a reward function","author":"Hejna","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref35","first-page":"70 247","article-title":"Direct preference-based policy optimization without reward modeling","volume":"36","author":"An","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","article-title":"Contrastive preference learning: Learning from human feedback without rl","volume-title":"International Conference on Learning Representations","author":"Hejna"},{"key":"ref37","first-page":"38 145","article-title":"Reward model learning vs. direct policy optimization: A comparative analysis of learning from human preferences","volume-title":"International Conference on Machine Learning","author":"Nika"},{"key":"ref38","article-title":"Is dpo superior to ppo for llm alignment? a comprehensive study","volume-title":"Forty-first International Conference on Machine Learning","author":"Xu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2024.3357618"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2314"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3408271"},{"key":"ref42","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref43","article-title":"Offline reinforcement learning with implicit q-learning","volume-title":"International Conference on Learning Representations","author":"Kostrikov"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.e4483"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247027.pdf?arnumber=11247027","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T19:46:19Z","timestamp":1776800779000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247027\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247027","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}